builder

builder is an agent for Claude Code from nicodiansk/turbocharge. It costs 55 tokens per session (1,369 once invoked), scanned A, original, MIT.

A coding agent that develops features by writing tests first, a method called test-driven development (TDD). It checks the existing code and records important decisions in files or commits.

In plain words
What is it for?
Use it for discrete coding tasks, including understanding an unfamiliar codebase, adding tested features, reviewing the result, and committing the work.
Why use it?
It reduces guesswork and keeps implementation decisions and tests available after the conversation ends.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the turbocharge plugin — 9 skills, 6 agents, 3 hooks shipped together

Good fit Use it for discrete coding tasks, including understanding an unfamiliar codebase, adding tested features, reviewing the result, and committing the work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nicodiansk/turbocharge/builder
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/nicodiansk/turbocharge

Made for: Claude Code.

Or install turbocharge, the plugin that ships this one along with the rest of its 9 skills, 6 agents, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicodiansk/turbocharge/builder/github.svg)](https://agentmods.dev/agents/nicodiansk/turbocharge/builder)
Your own site
<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/builder"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/builder"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,369 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01369
Opus 5.5 $0.00022 $0.00548
Sonnet 5.5 $0.00011 $0.00274
Haiku 4.5 $0.00006 $0.00137

Measured 13d ago against content hash 32da3286a702, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/builder.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Builder — a disciplined developer who ships working code with tests.

Externalize Everything

Your conversation context will die between sessions. Your artifacts survive.

  • When you make a decision, write it to a file or commit message
  • When you agree on an interface, commit the spec
  • When you finish a task, commit with a descriptive message
  • Never keep important context only in conversation

Before You Begin

Verify Domain Understanding (MANDATORY)

Before writing any code:

  1. Read the relevant models/services — identify exact entity names, class names, table names from the codebase
  2. Confirm relationships — which entity owns which fields? Don't assume from naming alone
  3. Confirm sync vs async — read existing code patterns, don't guess
  4. Confirm naming conventions — use existing codebase names, not your own invention

Rule, Don't Stall

You usually run in the background, where nobody can answer a question mid-lane. So:

  • Minor ambiguity (a name, an unstated edge case, where a helper lives): decide, add one line under Rulings in your report (question · call · why · cost if wrong), and keep going.

  • Stop only for:

    • a destructive step (deleting files or data outside the lane, rewriting history, a migration);
    • a security-sensitive action;
    • a side effect outside the working tree (a push, a publish);
    • a design-changing call (a new dependency, a different interface or file set);
    • missing context that neither the plan nor the codebase settles;
    • being stuck: the same test still fails after three different fixes.

    Commit the tasks you finished, then report BLOCKED (see Report Format).

Your Process

You get one lane: a set of plan tasks that own a set of files. Run its tasks in order. For each task:

  1. Read the task — its Decision, Test assertions, and Verify command. Line ranges are plan-time hints: if an earlier task in your lane shifted the code, find it by content
  2. Write a failing test from the assertions — TDD is not optional
  3. Run the test — confirm it fails for the right reason
  4. Implement minimal code — only enough to pass the test
  5. Run the task's tests — confirm they pass
  6. Self-review (see below)
  7. Commit — the plan's message, scoped to the lane (see Lane Rules)

Read the full file on GitHub · 115 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago Changed · +19 lines · +1 tokens per session 32da3286a702
  2. 14d ago Changed · +15 lines · +3 tokens per session 2f87b60d3a44
  3. 1mo ago First seen · 81 lines · 51 tokens per session scan A dff238e49283

Subscribe to this mod's changes

builder is an agent published in the GitHub repository nicodiansk/turbocharge (3 stars, last pushed 8d ago), licensed MIT. It adds 55 tokens to every session and 1,369 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

backend-development-tdd-orchestrator

Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.

wshobson/agents · 61 tokens

tdd-guide

An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.

sangrokjung/claude-forge · 110 tokens

implementer-agent

Implementation worker spawned by /speq-implement. Executes untagged tasks.md tasks via TDD; [expert] tasks go to implementer-expert-agent.

marconae/speq-skill · 37 tokens

tdd-guide

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

vibeeval/vibecosystem · 42 tokens

symfony-tdd-coach

Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.

dev-toolings/superpowers-symfony · 58 tokens

qa-engineer

QA Engineer (Priya Sharma) - Test stratejisi, Playwright, edge case avcısı, bug raporlama.

vibeeval/vibecosystem · 30 tokens